Set Options

knitr::opts_chunk$set(
  warning = TRUE, # show warnings during codebook generation
  message = TRUE, # show messages during codebook generation
  error = TRUE, # do not interrupt codebook generation in case of errors,
                # usually better for debugging
  echo = TRUE  # show R code
)
ggplot2::theme_set(ggplot2::theme_bw())

library(rio)
library(labelled)

Prep Data

library(codebook)
## 
## Attaching package: 'codebook'
## The following object is masked from 'package:labelled':
## 
##     to_factor
codebook_data <- import("../data_processing/output_data/priming_data/sr_prime_summary.csv")

# cat(paste(names(codebook_data), collapse = " = '', \n"))

var_label(codebook_data) <- list(
  target_word_unique = 'The target word shown in the study - if the target was used multiple times due to translation, it was given a .NUMBER at the end to be able to match related to unrelated trials.', 
  avgRT_related = 'The average response latency for related trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.', 
  avgRT_unrelated = 'The average response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.', 
  avgZ_RT_related = 'The average Z-scored response latency for related trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.', 
  avgZ_RT_unrelated = 'The average Z-scored response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.', 
  seRT_related = 'The standard error for the raw response latency related trials.', 
  seRT_unrelated = 'The standard error for the raw response latency unrelated trials.', 
  seZ_RT_related = 'The standard error for the Z-scored response latency related trials.', 
  seZ_RT_unrelated = 'The standard error for the Z-scored response latency unrelated trials.', 
  
  target_answeredN_related = 'The total number of people who answered the target trials when it was in a related condition.', 
  target_answeredN_unrelated = 'The total number of people who answered the target trials when it was in a unrelated condition.', 
  target_timeoutN_related = 'The total number of people who timed out on the target trials when it was in a related condition.', 
  target_timeoutN_unrelated = 'The total number of people who timed out on the target trials when it was in a unrelated condition.', 
  
  target_correct_keep_related = 'The number of correct answers kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  target_correct_keep_unrelated = 'The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  target_answeredN_keep_related = 'The number of answered trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  target_answeredN_keep_unrelated = 'The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  target_timeoutN_keep_related = 'The number of timeout trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  target_timeoutN_keep_unrelated = 'The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  target_prop_correct_keep_related = 'The proportion correct for related trials based on person and trial level exclusions.', 
  target_prop_correct_keep_unrelated = 'The proportion correct for unrelated trials based on person and trial level exclusions.', 
  
target_answeredN_related = 'The total number of people who answered the target trials when it was in a related condition.', 
  target_answeredN_unrelated = 'The total number of people who answered the target trials when it was in a unrelated condition.', 
  target_timeoutN_related = 'The total number of people who timed out on the target trials when it was in a related condition.', 
  target_timeoutN_unrelated = 'The total number of people who timed out on the target trials when it was in a unrelated condition.', 
  
  cue_correct_keep_related = 'The number of correct answers kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  cue_correct_keep_unrelated = 'The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  cue_answeredN_keep_related = 'The number of answered trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  cue_answeredN_keep_unrelated = 'The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  cue_timeoutN_keep_related = 'The number of timeout trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  cue_timeoutN_keep_unrelated = 'The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it\'s based on the number they saw).', 
  cue_prop_correct_keep_related = 'The proportion correct for related trials based on person and trial level exclusions.', 
  cue_prop_correct_keep_unrelated = 'The proportion correct for unrelated trials based on person and trial level exclusions.',  

  target_sample_keep_related = 'The final number of trials used in the Z-score average calculation.', 
  target_sample_keep_unrelated = 'The final number of trials used in the Z-score average calculation.', 
  avgRT_prime = 'The subtraction of the raw response latency for unrelated minus the raw response latency for related.', 
  avgZ_prime = 'The subtraction of the Z-scored response latency for unrelated minus the Z-scored latency for related.')

metadata(codebook_data)$name <- "Semantic Priming Across Many Languages Priming Summary Data"
metadata(codebook_data)$description <- "This dataset includes the summarized results of the priming trials, the number of trials for both cue and target, and other descriptive information. 

This codebook works for all files that say _summary_ in their name. If the file contains:

- _answered_: the exclusions are based on participants who made at least 80% correct by using number correct divided by number answered.
- does not say answered: the exclusions are based on participants who made at least 80% correct by using number correct divided by the number seen.
- _no2.5_: the Z-scores above 2.5 were excluded before any calculations. 
- _no3.0_: the Z-scores above 3.0 were excluded before any calculations. 
- Does not mention a number: all Z-scores are included. 
- Therefore, six combinations of files are included based on which scoring criterion and Z-score exclusion level you want to use. The Z-score exclusion level files do not contain all columns - the repetitive number of trial columns are excluded from those files (i.e., the number answered is the same no matter which Z-scored file is used, so it's only in the overall summary for each answered and non-answered file). The exclusions for sample size can be confusing, so we include a summary chart below. 

Semantic priming has been studied for nearly 50 years across various experimental manipulations and theoretical frameworks. These studies provide insight into the cognitive underpinnings of semantic representations in both healthy and clinical populations; however, they have suffered from several issues including generally low sample sizes and a lack of diversity in linguistic implementations. Here, we will test the size and the variability of the semantic priming effect across ten languages by creating a large database of semantic priming values, based on an adaptive sampling procedure. Differences in response latencies between related word-pair conditions and unrelated word-pair conditions (i.e., difference score confidence interval is greater than zero) will allow quantifying evidence for semantic priming, whereas improvements in model fit with the addition of a random intercept for language will provide support for variability in semantic priming across languages."
metadata(codebook_data)$identifier <- "https://doi.org/10.5281/zenodo.10888833"
metadata(codebook_data)$creator <- "Erin M. Buchanan"
metadata(codebook_data)$citation <- "Buchanan, E., Cuccolo, K., Heyman, T., Iyer, A., Coles, N., Lewis Jr, N., Peters, K., van Berkel, N., Taylor, J., Van't Veer, A. E., Montefinese, M., Valentine, K. D., Maxwell, N., Türkan, B. N., Williams, G., Oliveros-Chacana, J. C., Röer, J., Fini, C., Acar, O., … Lewis, S. C. (2024). SemanticPriming/SPAML: SPAML v1 Data Release (v1.0.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10888833"
metadata(codebook_data)$url <- "https://github.com/SemanticPriming/SPAML/releases/"
metadata(codebook_data)$datePublished <- "2024-05-01"
metadata(codebook_data)$temporalCoverage <- "2022-2024" 
metadata(codebook_data)$spatialCoverage <- "Online" 

Summary Chart

library(flextable)
library(rio)
summary_table <- import("sample_size_summary.xlsx")
flextable(
  summary_table
) %>% 
  add_footer_lines("Note. These columns also apply for cue values, and the star indicates either an unrelated or related trial for calculation.") %>%
  theme_zebra()

Variable

Description

Participant: < 18 years old

Participant: < 100 trials

Participant: < 80% correct

Trial: correct answer

Trial: not too fast, should be >=160

Trial: not too slow, should be < 3000

target_answeredN_*

All trials that ended in a response.

Included in calculation

Included in calculation

Included in calculation

Either correct or incorrect

All time durations included.

Specifically EXCLUDES timeout trials coded by the experiment. Sometimes "response" trials were over 3000 ms, they are included here.

target_timeoutN_*

All trials that ended in a timeout.

Included in calculation

Included in calculation

Included in calculation

Timeouts always marked as incorrect.

Timeout trials do not have a duration this short.

Specifically INCLUDES timeout trials coded by the experiment. Sometimes "response" trials were over 3000 ms, they are excluded here as they were marked as a response.

target_correct_keep_*

All trials that were kept by participant that were correct, regardless of timing exclusions.

Excluded in calculation

Excluded in calculation

Excluded in calculation

Only correct

All time durations included.

All time durations included.

target_answeredN_keep_*

All trials that were kept by participant, that ended in a response.

Excluded in calculation

Excluded in calculation

Excluded in calculation

Either correct or incorrect

All time durations included.

All time durations included.

target_timeoutN_keep_*

All trials that were kept by participant, that ended in a timeout.

Excluded in calculation

Excluded in calculation

Excluded in calculation

Timeouts always marked as incorrect.

Timeout trials do not have a duration this short.

Specifically INCLUDES timeout trials coded by the experiment. Sometimes "response" trials were over 3000 ms, they are excluded here as they were marked as a response.

target_prop_correct_keep_*

Target correct kept / target answered kept, so all participants who were kept, correct divided by answered.

Excluded in calculation

Excluded in calculation

Excluded in calculation

Only correct / all answered

All time durations included.

All time durations included.

target_sample_keep_*

Sample size with all exclusions applied.

Excluded in calculation

Excluded in calculation

Excluded in calculation

Only correct

Excluded too short.

Excluded too long and timeout trials.

Note. These columns also apply for cue values, and the star indicates either an unrelated or related trial for calculation.

Create codebook

codebook(codebook_data)
## No missing values.

Metadata

Description

Dataset name: Semantic Priming Across Many Languages Priming Summary Data

This dataset includes the summarized results of the priming trials, the number of trials for both cue and target, and other descriptive information.

This codebook works for all files that say summary in their name. If the file contains:

  • answered: the exclusions are based on participants who made at least 80% correct by using number correct divided by number answered.
  • does not say answered: the exclusions are based on participants who made at least 80% correct by using number correct divided by the number seen.
  • no2.5: the Z-scores above 2.5 were excluded before any calculations.
  • no3.0: the Z-scores above 3.0 were excluded before any calculations.
  • Does not mention a number: all Z-scores are included.
  • Therefore, six combinations of files are included based on which scoring criterion and Z-score exclusion level you want to use. The Z-score exclusion level files do not contain all columns - the repetitive number of trial columns are excluded from those files (i.e., the number answered is the same no matter which Z-scored file is used, so it’s only in the overall summary for each answered and non-answered file). The exclusions for sample size can be confusing, so we include a summary chart below.

Semantic priming has been studied for nearly 50 years across various experimental manipulations and theoretical frameworks. These studies provide insight into the cognitive underpinnings of semantic representations in both healthy and clinical populations; however, they have suffered from several issues including generally low sample sizes and a lack of diversity in linguistic implementations. Here, we will test the size and the variability of the semantic priming effect across ten languages by creating a large database of semantic priming values, based on an adaptive sampling procedure. Differences in response latencies between related word-pair conditions and unrelated word-pair conditions (i.e., difference score confidence interval is greater than zero) will allow quantifying evidence for semantic priming, whereas improvements in model fit with the addition of a random intercept for language will provide support for variability in semantic priming across languages.

Metadata for search engines
name value
1 Erin M. Buchanan
x
target_word_unique
avgRT_related
avgRT_unrelated
avgZ_RT_related
avgZ_RT_unrelated
seRT_related
seRT_unrelated
seZ_RT_related
seZ_RT_unrelated
target_answeredN_related
target_answeredN_unrelated
target_timeoutN_related
target_timeoutN_unrelated
target_correct_keep_related
target_correct_keep_unrelated
target_answeredN_keep_related
target_answeredN_keep_unrelated
target_timeoutN_keep_related
target_timeoutN_keep_unrelated
target_prop_correct_keep_related
target_prop_correct_keep_unrelated
cue_answeredN_related
cue_answeredN_unrelated
cue_timeoutN_related
cue_timeoutN_unrelated
cue_correct_keep_related
cue_correct_keep_unrelated
cue_answeredN_keep_related
cue_answeredN_keep_unrelated
cue_timeoutN_keep_related
cue_timeoutN_keep_unrelated
cue_prop_correct_keep_related
cue_prop_correct_keep_unrelated
target_sample_keep_related
target_sample_keep_unrelated
avgRT_prime
avgZ_prime

#Variables

target_word_unique

The target word shown in the study - if the target was used multiple times due to translation, it was given a .NUMBER at the end to be able to match related to unrelated trials.

Distribution

Distribution of values for target_word_unique

Distribution of values for target_word_unique

0 missing values.

Summary statistics

name label data_type n_missing complete_rate n_unique empty min max whitespace
target_word_unique The target word shown in the study - if the target was used multiple times due to translation, it was given a .NUMBER at the end to be able to match related to unrelated trials. character 0 1 1000 0 2 19 0

avgRT_unrelated

The average response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word answered in their file name.

Distribution

Distribution of values for avgRT_unrelated

Distribution of values for avgRT_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
avgRT_unrelated The average response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word answered in their file name. numeric 0 1 403 724 1300 753.0252 129.9062 ▁▇▅▁▁

avgZ_RT_unrelated

The average Z-scored response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word answered in their file name.

Distribution

Distribution of values for avgZ_RT_unrelated

Distribution of values for avgZ_RT_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
avgZ_RT_unrelated The average Z-scored response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word answered in their file name. numeric 0 1 -1.1 -0.45 1.3 -0.3724941 0.359167 ▅▇▃▁▁

seRT_unrelated

The standard error for the raw response latency unrelated trials.

Distribution

Distribution of values for seRT_unrelated

Distribution of values for seRT_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
seRT_unrelated The standard error for the raw response latency unrelated trials. numeric 0 1 12 39 207 40.76657 14.66497 ▇▂▁▁▁

seZ_RT_unrelated

The standard error for the Z-scored response latency unrelated trials.

Distribution

Distribution of values for seZ_RT_unrelated

Distribution of values for seZ_RT_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
seZ_RT_unrelated The standard error for the Z-scored response latency unrelated trials. numeric 0 1 0.042 0.094 0.55 0.0998481 0.038918 ▇▁▁▁▁

target_answeredN_unrelated

The total number of people who answered the target trials when it was in a unrelated condition.

Distribution

Distribution of values for target_answeredN_unrelated

Distribution of values for target_answeredN_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
target_answeredN_unrelated The total number of people who answered the target trials when it was in a unrelated condition. numeric 0 1 50 52 62 52.191 2.221138 ▇▂▁▁▁

target_timeoutN_unrelated

The total number of people who timed out on the target trials when it was in a unrelated condition.

Distribution

Distribution of values for target_timeoutN_unrelated

Distribution of values for target_timeoutN_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
target_timeoutN_unrelated The total number of people who timed out on the target trials when it was in a unrelated condition. numeric 0 1 0 1 6 1.364 1.184444 ▇▃▂▁▁

target_correct_keep_unrelated

The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw).

Distribution

Distribution of values for target_correct_keep_unrelated

Distribution of values for target_correct_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
target_correct_keep_unrelated The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw). numeric 0 1 3 48 59 47.587 4.16891 ▁▁▁▆▇

target_answeredN_keep_unrelated

The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw).

Distribution

Distribution of values for target_answeredN_keep_unrelated

Distribution of values for target_answeredN_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
target_answeredN_keep_unrelated The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw). numeric 0 1 41 49 60 48.935 2.641544 ▁▇▇▁▁

target_timeoutN_keep_unrelated

The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw).

Distribution

Distribution of values for target_timeoutN_keep_unrelated

Distribution of values for target_timeoutN_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
target_timeoutN_keep_unrelated The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw). numeric 0 1 0 0 4 0.294 0.554862 ▇▂▁▁▁

target_prop_correct_keep_unrelated

The proportion correct for unrelated trials based on person and trial level exclusions.

Distribution

Distribution of values for target_prop_correct_keep_unrelated

Distribution of values for target_prop_correct_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
target_prop_correct_keep_unrelated The proportion correct for unrelated trials based on person and trial level exclusions. numeric 0 1 0.061 0.98 1 0.9723698 0.0662805 ▁▁▁▁▇

cue_answeredN_unrelated

Distribution

Distribution of values for cue_answeredN_unrelated

Distribution of values for cue_answeredN_unrelated

0 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
cue_answeredN_unrelated numeric 0 1 48 52 62 52.145 2.269609 ▃▇▂▁▁ NA

cue_timeoutN_unrelated

Distribution

Distribution of values for cue_timeoutN_unrelated

Distribution of values for cue_timeoutN_unrelated

0 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
cue_timeoutN_unrelated numeric 0 1 0 1 6 1.41 1.23427 ▇▃▂▁▁ NA

cue_correct_keep_unrelated

The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw).

Distribution

Distribution of values for cue_correct_keep_unrelated

Distribution of values for cue_correct_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
cue_correct_keep_unrelated The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw). numeric 0 1 5 47 59 46.664 4.597634 ▁▁▁▇▅

cue_answeredN_keep_unrelated

The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw).

Distribution

Distribution of values for cue_answeredN_keep_unrelated

Distribution of values for cue_answeredN_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
cue_answeredN_keep_unrelated The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw). numeric 0 1 41 49 60 48.881 2.660812 ▁▇▇▁▁

cue_timeoutN_keep_unrelated

The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw).

Distribution

Distribution of values for cue_timeoutN_keep_unrelated

Distribution of values for cue_timeoutN_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
cue_timeoutN_keep_unrelated The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says answered in the file name, it is the exclusion based on the the number they answered, if not, it’s based on the number they saw). numeric 0 1 0 0 3 0.348 0.6043685 ▇▂▁▁▁

cue_prop_correct_keep_unrelated

The proportion correct for unrelated trials based on person and trial level exclusions.

Distribution

Distribution of values for cue_prop_correct_keep_unrelated

Distribution of values for cue_prop_correct_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
cue_prop_correct_keep_unrelated The proportion correct for unrelated trials based on person and trial level exclusions. numeric 0 1 0.1 0.98 1 0.9545342 0.0769903 ▁▁▁▁▇

target_sample_keep_unrelated

The final number of trials used in the Z-score average calculation.

Distribution

Distribution of values for target_sample_keep_unrelated

Distribution of values for target_sample_keep_unrelated

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
target_sample_keep_unrelated The final number of trials used in the Z-score average calculation. numeric 0 1 3 48 59 47.505 4.170056 ▁▁▁▇▇

avgRT_prime

The subtraction of the raw response latency for unrelated minus the raw response latency for related.

Distribution

Distribution of values for avgRT_prime

Distribution of values for avgRT_prime

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
avgRT_prime The subtraction of the raw response latency for unrelated minus the raw response latency for related. numeric 0 1 -329 47 427 51.00028 75.76532 ▁▂▇▂▁

avgZ_prime

The subtraction of the Z-scored response latency for unrelated minus the Z-scored latency for related.

Distribution

Distribution of values for avgZ_prime

Distribution of values for avgZ_prime

0 missing values.

Summary statistics

name label data_type n_missing complete_rate min median max mean sd hist
avgZ_prime The subtraction of the Z-scored response latency for unrelated minus the Z-scored latency for related. numeric 0 1 -1.1 0.13 0.94 0.1448051 0.1946609 ▁▁▇▇▁

Missingness report

Codebook table

JSON-LD metadata

The following JSON-LD can be found by search engines, if you share this codebook publicly on the web.

{
  "name": "Semantic Priming Across Many Languages Priming Summary Data",
  "description": "This dataset includes the summarized results of the priming trials, the number of trials for both cue and target, and other descriptive information. \n\nThis codebook works for all files that say _summary_ in their name. If the file contains:\n\n- _answered_: the exclusions are based on participants who made at least 80% correct by using number correct divided by number answered.\n- does not say answered: the exclusions are based on participants who made at least 80% correct by using number correct divided by the number seen.\n- _no2.5_: the Z-scores above 2.5 were excluded before any calculations. \n- _no3.0_: the Z-scores above 3.0 were excluded before any calculations. \n- Does not mention a number: all Z-scores are included. \n- Therefore, six combinations of files are included based on which scoring criterion and Z-score exclusion level you want to use. The Z-score exclusion level files do not contain all columns - the repetitive number of trial columns are excluded from those files (i.e., the number answered is the same no matter which Z-scored file is used, so it's only in the overall summary for each answered and non-answered file). The exclusions for sample size can be confusing, so we include a summary chart below. \n\nSemantic priming has been studied for nearly 50 years across various experimental manipulations and theoretical frameworks. These studies provide insight into the cognitive underpinnings of semantic representations in both healthy and clinical populations; however, they have suffered from several issues including generally low sample sizes and a lack of diversity in linguistic implementations. Here, we will test the size and the variability of the semantic priming effect across ten languages by creating a large database of semantic priming values, based on an adaptive sampling procedure. Differences in response latencies between related word-pair conditions and unrelated word-pair conditions (i.e., difference score confidence interval is greater than zero) will allow quantifying evidence for semantic priming, whereas improvements in model fit with the addition of a random intercept for language will provide support for variability in semantic priming across languages.\n\n\n## Table of variables\nThis table contains variable names, labels, and number of missing values.\nSee the complete codebook for more.\n\n[truncated]\n\n### Note\nThis dataset was automatically described using the [codebook R package](https://rubenarslan.github.io/codebook/) (version 0.9.2).",
  "identifier": "https://doi.org/10.5281/zenodo.10888833",
  "creator": "Erin M. Buchanan",
  "citation": "Buchanan, E., Cuccolo, K., Heyman, T., Iyer, A., Coles, N., Lewis Jr, N., Peters, K., van Berkel, N., Taylor, J., Van't Veer, A. E., Montefinese, M., Valentine, K. D., Maxwell, N., Türkan, B. N., Williams, G., Oliveros-Chacana, J. C., Röer, J., Fini, C., Acar, O., … Lewis, S. C. (2024). SemanticPriming/SPAML: SPAML v1 Data Release (v1.0.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10888833",
  "url": "https://github.com/SemanticPriming/SPAML/releases/",
  "datePublished": "2024-05-01",
  "temporalCoverage": "2022-2024",
  "spatialCoverage": "Online",
  "keywords": ["target_word_unique", "avgRT_related", "avgRT_unrelated", "avgZ_RT_related", "avgZ_RT_unrelated", "seRT_related", "seRT_unrelated", "seZ_RT_related", "seZ_RT_unrelated", "target_answeredN_related", "target_answeredN_unrelated", "target_timeoutN_related", "target_timeoutN_unrelated", "target_correct_keep_related", "target_correct_keep_unrelated", "target_answeredN_keep_related", "target_answeredN_keep_unrelated", "target_timeoutN_keep_related", "target_timeoutN_keep_unrelated", "target_prop_correct_keep_related", "target_prop_correct_keep_unrelated", "cue_answeredN_related", "cue_answeredN_unrelated", "cue_timeoutN_related", "cue_timeoutN_unrelated", "cue_correct_keep_related", "cue_correct_keep_unrelated", "cue_answeredN_keep_related", "cue_answeredN_keep_unrelated", "cue_timeoutN_keep_related", "cue_timeoutN_keep_unrelated", "cue_prop_correct_keep_related", "cue_prop_correct_keep_unrelated", "target_sample_keep_related", "target_sample_keep_unrelated", "avgRT_prime", "avgZ_prime"],
  "@context": "http://schema.org/",
  "@type": "Dataset",
  "variableMeasured": [
    {
      "name": "target_word_unique",
      "description": "The target word shown in the study - if the target was used multiple times due to translation, it was given a .NUMBER at the end to be able to match related to unrelated trials.",
      "@type": "propertyValue"
    },
    {
      "name": "avgRT_related",
      "description": "The average response latency for related trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.",
      "@type": "propertyValue"
    },
    {
      "name": "avgRT_unrelated",
      "description": "The average response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.",
      "@type": "propertyValue"
    },
    {
      "name": "avgZ_RT_related",
      "description": "The average Z-scored response latency for related trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.",
      "@type": "propertyValue"
    },
    {
      "name": "avgZ_RT_unrelated",
      "description": "The average Z-scored response latency for unrelated trials - using our exclusion rules for both targets and people. Trials: not too long < 3000 ms, not too short > 160ms, correctly answered; People: must be 18 years old, saw at least 100 trials, correctly answered at least 80% of the trials SEEN for files that just say priming_summary, and ANSWERED for files that use the word _answered_ in their file name.",
      "@type": "propertyValue"
    },
    {
      "name": "seRT_related",
      "description": "The standard error for the raw response latency related trials.",
      "@type": "propertyValue"
    },
    {
      "name": "seRT_unrelated",
      "description": "The standard error for the raw response latency unrelated trials.",
      "@type": "propertyValue"
    },
    {
      "name": "seZ_RT_related",
      "description": "The standard error for the Z-scored response latency related trials.",
      "@type": "propertyValue"
    },
    {
      "name": "seZ_RT_unrelated",
      "description": "The standard error for the Z-scored response latency unrelated trials.",
      "@type": "propertyValue"
    },
    {
      "name": "target_answeredN_related",
      "description": "The total number of people who answered the target trials when it was in a related condition.",
      "@type": "propertyValue"
    },
    {
      "name": "target_answeredN_unrelated",
      "description": "The total number of people who answered the target trials when it was in a unrelated condition.",
      "@type": "propertyValue"
    },
    {
      "name": "target_timeoutN_related",
      "description": "The total number of people who timed out on the target trials when it was in a related condition.",
      "@type": "propertyValue"
    },
    {
      "name": "target_timeoutN_unrelated",
      "description": "The total number of people who timed out on the target trials when it was in a unrelated condition.",
      "@type": "propertyValue"
    },
    {
      "name": "target_correct_keep_related",
      "description": "The number of correct answers kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "target_correct_keep_unrelated",
      "description": "The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "target_answeredN_keep_related",
      "description": "The number of answered trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "target_answeredN_keep_unrelated",
      "description": "The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "target_timeoutN_keep_related",
      "description": "The number of timeout trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "target_timeoutN_keep_unrelated",
      "description": "The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "target_prop_correct_keep_related",
      "description": "The proportion correct for related trials based on person and trial level exclusions.",
      "@type": "propertyValue"
    },
    {
      "name": "target_prop_correct_keep_unrelated",
      "description": "The proportion correct for unrelated trials based on person and trial level exclusions.",
      "@type": "propertyValue"
    },
    {
      "name": "cue_answeredN_related",
      "@type": "propertyValue"
    },
    {
      "name": "cue_answeredN_unrelated",
      "@type": "propertyValue"
    },
    {
      "name": "cue_timeoutN_related",
      "@type": "propertyValue"
    },
    {
      "name": "cue_timeoutN_unrelated",
      "@type": "propertyValue"
    },
    {
      "name": "cue_correct_keep_related",
      "description": "The number of correct answers kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "cue_correct_keep_unrelated",
      "description": "The number of correct answers kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "cue_answeredN_keep_related",
      "description": "The number of answered trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "cue_answeredN_keep_unrelated",
      "description": "The number of answered trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "cue_timeoutN_keep_related",
      "description": "The number of timeout trials kept based on trial and person level exclusions in the study for related trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "cue_timeoutN_keep_unrelated",
      "description": "The number of timeout trials kept based on trial and person level exclusions in the study for unrelated trials (person level depends on the file you use - if it says _answered_ in the file name, it is the exclusion based on the the number they answered, if not, it's based on the number they saw).",
      "@type": "propertyValue"
    },
    {
      "name": "cue_prop_correct_keep_related",
      "description": "The proportion correct for related trials based on person and trial level exclusions.",
      "@type": "propertyValue"
    },
    {
      "name": "cue_prop_correct_keep_unrelated",
      "description": "The proportion correct for unrelated trials based on person and trial level exclusions.",
      "@type": "propertyValue"
    },
    {
      "name": "target_sample_keep_related",
      "description": "The final number of trials used in the Z-score average calculation.",
      "@type": "propertyValue"
    },
    {
      "name": "target_sample_keep_unrelated",
      "description": "The final number of trials used in the Z-score average calculation.",
      "@type": "propertyValue"
    },
    {
      "name": "avgRT_prime",
      "description": "The subtraction of the raw response latency for unrelated minus the raw response latency for related.",
      "@type": "propertyValue"
    },
    {
      "name": "avgZ_prime",
      "description": "The subtraction of the Z-scored response latency for unrelated minus the Z-scored latency for related.",
      "@type": "propertyValue"
    }
  ]
}`